I have been trying to run Qwen Coder models (8B at 4bit) on my M3 Pro 18GB behin... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		sidchilling 17 hours ago \| parent \| context \| favorite \| on: Can I run AI locally? I have been trying to run Qwen Coder models (8B at 4bit) on my M3 Pro 18GB behind Ollama and connecting codex CLI to it. The tool usage seems practically zero, like it returns the tool call in text JSON and codex CLI doesn’t run the tool (just displays the tool call in text). Has anyone succeeded in doing something like this? What am I missing?

		help

mongrelion 16 hours ago | [–]

It might be that the system prompt sent by codex is not optimal for that model. Try with open code and see if your results improve

MikeNotThePope 17 hours ago | [–]

I have the same hardware. Been curious about trying it with Opencode.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact